Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اظ
    -0.06
     Рас
    -0.06
     slider
    -0.06
     hockey
    -0.06
    (SDL
    -0.06
    итив
    -0.06
     bàn
    -0.06
     fists
    -0.06
     इक
    -0.06
    %',
    -0.06
    POSITIVE LOGITS
    vertisement
    0.07
    ynom
    0.07
    fin
    0.06
     ll
    0.06
     Priv
    0.06
     misc
    0.06
     tạo
    0.06
    放
    0.06
     executable
    0.06
    ム
    0.06
    Act Density 0.000%

    No Known Activations